{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J2IXHTRNAKC43XZNB6ROY53565","short_pith_number":"pith:J2IXHTRN","schema_version":"1.0","canonical_sha256":"4e9173ce2d0285cddf2d0fa2ec777df77dee18adac1dd0dbaca839f33e899e0e","source":{"kind":"arxiv","id":"2505.21857","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Bayesian Model Averaging in the Era of Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mijung Park","submitted_at":"2025-05-28T01:03:28Z","abstract_excerpt":"We revisit the classical, full-fledged Bayesian model averaging (BMA) paradigm to ensemble pre-trained and/or lightly-finetuned foundation models to enhance the classification performance on image and text data. To make BMA tractable under foundation models, we introduce trainable linear classifiers that take frozen features from the pre-trained foundation models as inputs. The model posteriors over the linear classifiers tell us which linear heads and frozen features are better suited for a given dataset, resulting in a principled model ensembling method. Furthermore, we propose a computation"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.21857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T01:03:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90105e9e37b6dbb0d1c74267229ba30e4da7f5d394c8507803130ba7fed1069b","abstract_canon_sha256":"6ab9d46a778d4e42377a2cbc2c2d8236724a0916656187e69c489d3bcc6dd883"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:04.886821Z","signature_b64":"t9SOHrqJaJon4VjEMzQSh4XrWBxziH5+KKBbHUsnkSIHLF1H9/HoK0VCODasobMXYSlspxbvEO9isCx2mYK5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e9173ce2d0285cddf2d0fa2ec777df77dee18adac1dd0dbaca839f33e899e0e","last_reissued_at":"2026-07-05T11:11:04.886396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:04.886396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Bayesian Model Averaging in the Era of Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mijung Park","submitted_at":"2025-05-28T01:03:28Z","abstract_excerpt":"We revisit the classical, full-fledged Bayesian model averaging (BMA) paradigm to ensemble pre-trained and/or lightly-finetuned foundation models to enhance the classification performance on image and text data. To make BMA tractable under foundation models, we introduce trainable linear classifiers that take frozen features from the pre-trained foundation models as inputs. The model posteriors over the linear classifiers tell us which linear heads and frozen features are better suited for a given dataset, resulting in a principled model ensembling method. Furthermore, we propose a computation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21857","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.21857/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.21857","created_at":"2026-07-05T11:11:04.886453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21857v1","created_at":"2026-07-05T11:11:04.886453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21857","created_at":"2026-07-05T11:11:04.886453+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2IXHTRNAKC4","created_at":"2026-07-05T11:11:04.886453+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2IXHTRNAKC43XZN","created_at":"2026-07-05T11:11:04.886453+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2IXHTRN","created_at":"2026-07-05T11:11:04.886453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565","json":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565.json","graph_json":"https://pith.science/api/pith-number/J2IXHTRNAKC43XZNB6ROY53565/graph.json","events_json":"https://pith.science/api/pith-number/J2IXHTRNAKC43XZNB6ROY53565/events.json","paper":"https://pith.science/paper/J2IXHTRN"},"agent_actions":{"view_html":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565","download_json":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565.json","view_paper":"https://pith.science/paper/J2IXHTRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21857&json=true","fetch_graph":"https://pith.science/api/pith-number/J2IXHTRNAKC43XZNB6ROY53565/graph.json","fetch_events":"https://pith.science/api/pith-number/J2IXHTRNAKC43XZNB6ROY53565/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565/action/storage_attestation","attest_author":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565/action/author_attestation","sign_citation":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565/action/citation_signature","submit_replication":"https://pith.science/pith/J2IXHTRNAKC43XZNB6ROY53565/action/replication_record"}},"created_at":"2026-07-05T11:11:04.886453+00:00","updated_at":"2026-07-05T11:11:04.886453+00:00"}